import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.ticker import ScalarFormatter
import seaborn as sb
import warnings
warnings.filterwarnings('ignore', category=FutureWarning)
import zipfile

pd.set_option('display.max_columns', 700)
pd.set_option('display.max_colwidth', 100)

pisadict2012 = pd.read_csv('./data/pisadict2012.csv', encoding='latin-1', low_memory=False, index_col=0).T

pisadict2012

with zipfile.ZipFile('./data/pisa2012.csv.zip', 'r') as zip_ref:
    with zip_ref.open('pisa2012.csv') as csv_file:
        pisa2012 = pd.read_csv(csv_file, encoding='latin-1', low_memory=False, index_col=0)

pisa2012.head()

pisa2012.info()

<class 'pandas.core.frame.DataFrame'>
Index: 485490 entries, 1 to 485490
Columns: 635 entries, CNT to VER_STU
dtypes: float64(250), int64(17), object(368)
memory usage: 2.3+ GB

', '.join(pisa2012.NC.unique())

'Albania, United Arab Emirates , Argentina, Australia, Austria, Belgium, Bulgaria , Brazil , Canada , Switzerland, Chile, Colombia , Costa Rica , Czech Republic , Germany, Denmark, Spain, Estonia, Finland, France , United Kingdom (excl.Scotland) , United Kingdom (Scotland), Greece , Hong Kong-China, Croatia, Hungary, Indonesia, Ireland, Iceland, Israel , Italy, Jordan , Japan, Kazakhstan , Republic of Korea, Liechtenstein, Lithuania, Luxembourg , Latvia , Macao-China, Mexico , Montenegro , Malaysia , Netherlands, Norway , New Zealand, Peru , Poland , Portugal , Qatar, China (Shanghai) , Perm (Russian Federation), United States of America , Romania, Russian Federation , Singapore, Serbia , Slovak Republic, Slovenia , Sweden , Chinese Taipei , Thailand , Tunisia, Turkey , Uruguay, Viet Nam '

dummy_columns =    ['NC', 'ST03Q01', 'ST03Q02', 'ST04Q01',
    'PV1MATH', 'PV2MATH', 'PV3MATH', 'PV4MATH', 'PV5MATH',
    'PV1READ', 'PV2READ', 'PV3READ', 'PV4READ', 'PV5READ',
    'PV1SCIE', 'PV2SCIE', 'PV3SCIE', 'PV4SCIE', 'PV5SCIE']

dict = {
    'AGE': 'Age',
    'HISEI': 'Occupational',
    'PARED': 'Education',
    'HOMEPOS': 'Home Setup',
    'ESCS': 'Socioeconomic'
}

NC_renaming = {
    "United Kingdom (excl.Scotland)": "United Kingdom",
    "United Kingdom (Scotland)": "United Kingdom",
    "Hong Kong-China": "Greater China\n (excl.Mainland)",
    "Macao-China": "Greater China\n (excl.Mainland)",
    "China (Shanghai)": "Greater China\n (excl.Mainland)",
    "Perm (Russian Federation)": "Russian Federation",
    "United States of America" :"USA",
    "Singapore": "Greater China\n (excl.Mainland)",
    "Chinese Taipei": "Greater China\n (excl.Mainland)"
}

selected_columns = list(dict.keys()) + dummy_columns
pisadict2012clean = pisadict2012[selected_columns].rename(columns=dict)
pisa2012clean = pisa2012[selected_columns].rename(columns=dict)

Dependencies = ['Education', 'Occupational', 'Home Setup']
Subjects = ['Math', 'Reading', 'Science']

pisa2012clean['Country'] = pisa2012clean['NC'].str.rstrip().replace(NC_renaming)
pisa2012clean['Male'] = pisa2012clean['ST04Q01'].map({'Male': 1, 'Female': 0})
pisa2012clean['Math'] = pisa2012clean[[f'PV{i}MATH' for i in range(1, 6)]].mean(axis=1)
pisa2012clean['Reading'] = pisa2012clean[[f'PV{i}READ' for i in range(1, 6)]].mean(axis=1)
pisa2012clean['Science'] = pisa2012clean[[f'PV{i}SCIE' for i in range(1, 6)]].mean(axis=1)
pisa2012clean['Total'] = pisa2012clean[Subjects].mean(axis=1)

pisadict2012clean = pisadict2012clean.loc[:, ~pisadict2012clean.columns.isin(dummy_columns)]
pisa2012clean = pisa2012clean.loc[:, ~pisa2012clean.columns.isin(dummy_columns)]

Total_mean = pisa2012clean.groupby('Country')['Total'].mean()
order = Total_mean.sort_values(ascending=False).index.tolist()

pisadict2012clean.T

pisa2012clean.info()

<class 'pandas.core.frame.DataFrame'>
Index: 485490 entries, 1 to 485490
Data columns (total 11 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Age            485374 non-null  float64
 1   Occupational   450621 non-null  float64
 2   Education      473091 non-null  float64
 3   Home Setup     479807 non-null  float64
 4   Socioeconomic  473648 non-null  float64
 5   Country        485490 non-null  object 
 6   Male           485490 non-null  int64  
 7   Math           485490 non-null  float64
 8   Reading        485490 non-null  float64
 9   Science        485490 non-null  float64
 10  Total          485490 non-null  float64
dtypes: float64(9), int64(1), object(1)
memory usage: 44.4+ MB

# Creating a histogram to visualize the distribution of total performance
plt.figure(figsize=(10, 6))
sb.histplot(pisa2012clean['Total'], kde=True, bins=30, color='skyblue')

# Setting the title, x-axis label, and y-axis label
plt.title('Distribution of Total Performance')
plt.xlabel('Total Performance')
plt.ylabel('Number of Participants');

plt.figure(figsize=(10, 6))

# Plotting the histogram of educational levels
sb.histplot(pisa2012clean['Education'], bins=20, color='purple')

# Setting the title, x-axis label, and y-axis label
plt.title('Distribution of Educational Levels')
plt.xlabel('Years of Education')
plt.ylabel('Number of Participants');

# Plotting the histogram of age distribution
plt.figure(figsize=(10, 6))
sb.histplot(pisa2012clean['Age'], bins=30, color='green')

# Setting the title, x-axis label, and y-axis label
plt.title('Age Distribution of Participants')
plt.xlabel('Age')
plt.ylabel('Number of Participants');

# Creating a boxplot to visualize math performance by gender
plt.figure(figsize=(10, 6))
sb.boxplot(x='Male', y='Math', data=pisa2012clean, palette='pastel')

# Setting the title, x-axis label, and y-axis label
plt.title('Math Performance by Gender')
plt.xlabel('Gender (0 = Female, 1 = Male)')
plt.ylabel('Math Performance');

# Plotting boxplot for Math performance by Age groups
plt.figure(figsize=(12, 8))
sb.boxplot(x='Age', y='Math', data=pisa2012clean, color='blue')

# Setting the title, x-axis label, and y-axis label
plt.title('Math Performance by Age Groups')
plt.xlabel('Age')
plt.ylabel('Math Performance')

# Rotating x-axis labels for better readability
plt.xticks(rotation=45);

# Create scatter plot
plt.figure(figsize=(10, 6))
sb.scatterplot(x='Socioeconomic', y='Total', data=pisa2012clean, hue='Male', palette='coolwarm', alpha=.6)

# Set title and axis labels
plt.title('Relationship Between Socioeconomic Status and Total Performance')
plt.xlabel('Socioeconomic Index')
plt.ylabel('Total Performance');

# Calculating the average socioeconomic status by country and sorting the values
average_socioeconomic_by_country = pisa2012clean.groupby('Country')['Socioeconomic'].mean().sort_values()

# Plotting the bar chart
plt.figure(figsize=(25, 8))
average_socioeconomic_by_country.plot(kind='bar', color='orange')

# Setting the title, x-axis label, and y-axis label
plt.title('Average Socioeconomic Status by Country')
plt.xlabel('Country')
plt.ylabel('Average Socioeconomic Status')

# Rotating x-axis labels for better readability
plt.xticks(rotation=45, ha="right");

# Grouping data by 'Country' and 'Male' and calculating the average reading performance
average_reading_by_gender_country = pisa2012clean.groupby(['Country', 'Male'])['Reading'].mean().unstack()

# Sorting the data based on the specified order
average_reading_by_gender_country = average_reading_by_gender_country.loc[order]

# Plotting the bar chart
average_reading_by_gender_country.plot(kind='bar', figsize=(25, 8), color=['orange','blue'])

# Setting the title, x-axis label, and y-axis label
plt.title('Average Reading Performance by Gender and Country')
plt.xlabel('Country')
plt.ylabel('Average Reading Performance')

# Rotating x-axis labels for better readability
plt.xticks(rotation=45, ha="right")

# Adding legend
plt.legend(title='Gender', labels=['Female', 'Male']);

# Counting the distribution of genders
gender_counts = pisa2012clean['Male'].value_counts()

# Plotting the pie chart
plt.figure(figsize=(6, 6))
plt.pie(gender_counts, labels=['Female', 'Male'], autopct='%1.1f%%', startangle=90, colors=['orange','blue'])

# Setting the title for the plot
plt.title('Gender Distribution of Participants');

# Create a figure with a specific size
plt.figure(figsize=(6, 6))

# Plot a cumulative histogram of 'Socioeconomic' pisa2012clean
sb.histplot(pisa2012clean['Socioeconomic'], bins=30, cumulative=True, element="step", fill=False, color='navy')

# Set title, x-axis label, and y-axis label
plt.title('Cumulative Distribution of Socioeconomic Status')
plt.xlabel('Socioeconomic Status')
plt.ylabel('Cumulative Number of Participants');

plt.figure(figsize=(25, 8))
    
# Plotting countplot with x and y axes swapped and applying order to countries
sb.countplot(x='Country', data=pisa2012clean, order=order, color='blue')
    
# Setting plot title, labels, and displaying the plot
plt.title('Number of Participants by Country')
plt.xlabel('Country')
plt.ylabel('Number of Participants')
plt.xticks(rotation=45, ha="right");

# Group pisa2012clean by 'Country' and calculate percentage distribution of 'Male' values
gender_distribution_per_country = pisa2012clean.groupby('Country')['Male'].value_counts(normalize=True).unstack().fillna(0) * 100
# Reorder the rows based on the specified order
gender_distribution_per_country = gender_distribution_per_country.loc[order]

# Plotting
gender_distribution_per_country.plot(kind='bar', stacked=True, color=['orange','blue'], figsize=(25, 8))

# Setting plot title, labels, and legend
plt.title('Percentage of Male and Female Participants by Country')
plt.xlabel('Country')
plt.ylabel('Percentage')
plt.xticks(rotation=45, ha="right")
plt.legend(title='Gender', labels=['Female', 'Male']);

def plot_average_total_score():
    # Calculating mean total scores for males and females by country
    male_mean = pisa2012clean.query("Male == 1").groupby('Country')['Total'].mean()
    female_mean = pisa2012clean.query("Male == 0").groupby('Country')['Total'].mean()

    # Setting up y-axis ticks
    ybins = np.arange(10, 900 + 20, 20)
    yticks = ybins[::1] - 10

    # Creating the plot
    fig, ax1 = plt.subplots(figsize=(25, 10))
    plt.yticks(yticks)
    plt.xticks(rotation=60, ha='right')
    
    # Boxplot showing the interquartile range (IQR)
    sb.boxplot(data=pisa2012clean, x='Country', y='Total', order=order, showfliers=False, whis=0, color='lightgray', ax=ax1, width=.5, linewidth=.5)
    
    # Adding gridlines
    plt.grid(True, linestyle='--', linewidth=.3)

    # Plotting average markers for each country
    for i, country in enumerate(order):
        mean_val = Total_mean[country]
        mean_val_male = male_mean[country]
        mean_val_female = female_mean[country]
 
        ax1.plot(i, mean_val_male, marker='o', color='blue', markersize=8)
        ax1.plot(i, mean_val_female, marker='o', color='orange', markersize=8)
        ax1.plot(i, mean_val, marker='x', color='black', markersize=8)

    # Setting labels and title
    ax1.set_ylabel('Total Scores', fontsize=16)
    ax1.set_xlabel('')
    plt.title('Total Scores: IQR with Avg. Markers by Countries', fontsize=24)
    
    # Adding legend
    legend_labels = ['Total Avg.', 'Male Avg.', 'Female Avg.']
    legend_handles = [plt.Line2D([0], [0], marker='x', color='black', markersize=24, linestyle='None'),
                      plt.Line2D([0], [0], marker='o', color='blue', markersize=24, linestyle='None'),
                      plt.Line2D([0], [0], marker='o', color='orange', markersize=24, linestyle='None')]
    plt.legend(legend_handles, legend_labels, fontsize=24)

plot_average_total_score()

def plot_score_distribution(pisa_2012_clean, Subjects):
    # Create a figure with appropriate size
    plt.figure(figsize=[25, 1+9/len(Subjects)])
    
    # Define bin edges for x and y axes
    xbins = np.arange(10, 900 + 20, 20)
    ybins = np.arange(0, .0042 + .0002, .0002)
    
    # Define tick locations for x and y axes
    xticks = xbins[::len(Subjects)] - 10
    yticks = ybins[::len(Subjects)]
    
    # Iterate over each subject and plot the distribution by gender
    for col_index, Subject in enumerate(Subjects):
        ax = plt.subplot(1, len(Subjects), col_index + 1)
        
        # Plot kernel density estimate (KDE) for male and female scores
        sb.kdeplot(data=pisa_2012_clean[pisa_2012_clean['Male'] == 1][Subject], label='Male', color='blue', ax=ax)
        sb.kdeplot(data=pisa_2012_clean[pisa_2012_clean['Male'] == 0][Subject], label='Female', color='orange', ax=ax)    
        
        # Set tick locations and labels for x and y axes
        ax.set_xticks(xticks)
        ax.set_yticks(yticks)
        ax.set_xticklabels(xticks, rotation=15) 
        ax.set_yticklabels((yticks*1000).round(1))
        
        # Add grid lines and set axis limits
        ax.grid(axis='y', linestyle='--', alpha=.5)
        ax.set_xlim(0, 910)
        ax.set_ylim(0, .0042)
        
        # Set title, x-axis label, and y-axis label
        ax.set_title(Subject, fontsize=16)
        ax.set_xlabel(f'{Subject} Scores', fontsize=16)
        ax.set_ylabel('Parts per thousand' if col_index == 0 else '', fontsize=16)
        
        # Add legend
        ax.legend(loc='lower center', fontsize=8+24/len(Subjects))

    # Set super title
    plt.suptitle(f'Distribution of Student Scores {"across Subjects " if Subjects != ["Total"] else ""}by Gender', fontsize=24, y=.89+len(Subjects)/18)

plot_score_distribution(pisa2012clean, Subjects=['Total'])

plot_score_distribution(pisa2012clean, Subjects)

def plot_dependent_distribution(pisa_2012_clean, Subjects, Dependencies):
    # Create subplots grid
    fig, axs = plt.subplots(len(Dependencies), len(Subjects), figsize=(25, 12), squeeze=False)   
    
    # Define bins and xticks
    bins = np.arange(10, 900 + 20, 20)
    xticks = bins[::len(Subjects)] - 10

    # Iterate over rows and columns
    for row_index, Dependency in enumerate(Dependencies):
        for col_index, Subject in enumerate(Subjects):
            # Add jitter to the dependent variable
            jittered_dependent = pisa_2012_clean[Dependency] + np.random.uniform(-.35, .35, size=len(pisa_2012_clean))
            # Calculate correlation coefficient
            correlation = pisa_2012_clean[Subject].corr(pisa_2012_clean[Dependency])
            # Create hexbin plot
            hb = axs[row_index, col_index].hexbin(pisa_2012_clean[Subject], jittered_dependent, bins='log', vmin=1, vmax=2000)
            
            # Customize x-axis
            axs[row_index, col_index].set_xticks(xticks)
            axs[row_index, col_index].set_xticklabels(xticks, rotation=15)
            axs[row_index, col_index].set_xlim(0, 910)
            
            # Add correlation coefficient text
            axs[row_index, col_index].text(.84, .02, f'ρ = {correlation:.2f}', transform=axs[row_index, col_index].transAxes, fontsize=54/len(Subjects)-4)
            
            # Set title, x-axis label, and y-axis label
            axs[row_index, col_index].set_title(f'{Subject} | {Dependency}', fontsize=10)
            axs[row_index, col_index].set_xlabel(f'{Subject} Scores' if row_index == len(Dependencies)-1 else '', fontsize=16)
            axs[row_index, col_index].set_ylabel(f'{Dependency} Index' if col_index == 0 else '', fontsize=16)

        # Add colorbar
        cbar_ax = fig.add_axes([.91, .11 + row_index * .272, .01, (.815 / len(Dependencies))-.045])
        cbar = fig.colorbar(hb, cax=cbar_ax)
        cbar.set_ticks([1, 2, 5, 10, 20, 50, 100, 200, 500, 1000, 2000])
        cbar.ax.yaxis.set_major_formatter(ScalarFormatter())
        cbar.set_label('Frequency', fontsize=16)

    # Add overall title
    plt.suptitle(f'Distribution of Student Scores {(Subjects != ["Total"]) * "across Subjects "}depending on Parental Factors{(Dependencies == ["Socioeconomic"]) * " together"}', fontsize=24, y=.93)

plot_dependent_distribution(pisa2012clean, Subjects=["Total"], Dependencies=["Socioeconomic"])

plot_dependent_distribution(pisa2012clean, Subjects, Dependencies)

pisadict2012clean.T.to_csv('./data/pisadict2012clean.csv')
pisa2012clean.to_csv('./data/pisa2012clean.csv', index=False)

	CNT	SUBNATIO	STRATUM	OECD	NC	SCHOOLID	STIDSTD	ST01Q01	ST02Q01	ST03Q01	ST03Q02	ST04Q01	ST05Q01	ST06Q01	ST07Q01	ST07Q02	ST07Q03	ST08Q01	ST09Q01	ST115Q01	ST11Q01	ST11Q02	ST11Q03	ST11Q04	ST11Q05	ST11Q06	ST13Q01	ST14Q01	ST14Q02	ST14Q03	ST14Q04	ST15Q01	ST17Q01	ST18Q01	ST18Q02	ST18Q03	ST18Q04	ST19Q01	ST20Q01	ST20Q02	ST20Q03	ST21Q01	ST25Q01	ST26Q01	ST26Q02	ST26Q03	ST26Q04	ST26Q05	ST26Q06	ST26Q07	ST26Q08	ST26Q09	ST26Q10	ST26Q11	ST26Q12	ST26Q13	ST26Q14	ST26Q15	ST26Q16	ST26Q17	ST27Q01	ST27Q02	ST27Q03	ST27Q04	ST27Q05	ST28Q01	ST29Q01	ST29Q02	ST29Q03	ST29Q04	ST29Q05	ST29Q06	ST29Q07	ST29Q08	ST35Q01	ST35Q02	ST35Q03	ST35Q04	ST35Q05	ST35Q06	ST37Q01	ST37Q02	ST37Q03	ST37Q04	ST37Q05	ST37Q06	ST37Q07	ST37Q08	ST42Q01	ST42Q02	ST42Q03	ST42Q04	ST42Q05	ST42Q06	ST42Q07	ST42Q08	ST42Q09	ST42Q10	ST43Q01	ST43Q02	ST43Q03	ST43Q04	ST43Q05	ST43Q06	ST44Q01	ST44Q03	ST44Q04	ST44Q05	ST44Q07	ST44Q08	ST46Q01	ST46Q02	ST46Q03	ST46Q04	ST46Q05	ST46Q06	ST46Q07	ST46Q08	ST46Q09	ST48Q01	ST48Q02	ST48Q03	ST48Q04	ST48Q05	ST49Q01	ST49Q02	ST49Q03	ST49Q04	ST49Q05	ST49Q06	ST49Q07	ST49Q09	ST53Q01	ST53Q02	ST53Q03	ST53Q04	ST55Q01	ST55Q02	ST55Q03	ST55Q04	ST57Q01	ST57Q02	ST57Q03	ST57Q04	ST57Q05	ST57Q06	ST61Q01	ST61Q02	ST61Q03	ST61Q04	ST61Q05	ST61Q06	ST61Q07	ST61Q08	ST61Q09	ST62Q01	ST62Q02	ST62Q03	ST62Q04	ST62Q06	ST62Q07	ST62Q08	ST62Q09	ST62Q10	ST62Q11	ST62Q12	ST62Q13	ST62Q15	ST62Q16	ST62Q17	ST62Q19	ST69Q01	ST69Q02	ST69Q03	ST70Q01	ST70Q02	ST70Q03	ST71Q01	ST72Q01	ST73Q01	ST73Q02	ST74Q01	ST74Q02	ST75Q01	ST75Q02	ST76Q01	ST76Q02	ST77Q01	ST77Q02	ST77Q04	ST77Q05	ST77Q06	ST79Q01	ST79Q02	ST79Q03	ST79Q04	ST79Q05	ST79Q06	ST79Q07	ST79Q08	ST79Q10	ST79Q11	ST79Q12	ST79Q15	ST79Q17	ST80Q01	ST80Q04	ST80Q05	ST80Q06	ST80Q07	ST80Q08	ST80Q09	ST80Q10	ST80Q11	ST81Q01	ST81Q02	ST81Q03	ST81Q04	ST81Q05	ST82Q01	ST82Q02	ST82Q03	ST83Q01	ST83Q02	ST83Q03	ST83Q04	ST84Q01	ST84Q02	ST84Q03	ST85Q01	ST85Q02	ST85Q03	ST85Q04	ST86Q01	ST86Q02	ST86Q03	ST86Q04	ST86Q05	ST87Q01	ST87Q02	ST87Q03	ST87Q04	ST87Q05	ST87Q06	ST87Q07	ST87Q08	ST87Q09	ST88Q01	ST88Q02	ST88Q03	ST88Q04	ST89Q02	ST89Q03	ST89Q04	ST89Q05	ST91Q01	ST91Q02	ST91Q03	ST91Q04	ST91Q05	ST91Q06	ST93Q01	ST93Q03	ST93Q04	ST93Q06	ST93Q07	ST94Q05	ST94Q06	ST94Q09	ST94Q10	ST94Q14	ST96Q01	ST96Q02	ST96Q03	ST96Q05	ST101Q01	ST101Q02	ST101Q03	ST101Q05	ST104Q01	ST104Q04	ST104Q05	ST104Q06	IC01Q01	IC01Q02	IC01Q03	IC01Q04	IC01Q05	IC01Q06	IC01Q07	IC01Q08	IC01Q09	IC01Q10	IC01Q11	IC02Q01	IC02Q02	IC02Q03	IC02Q04	IC02Q05	IC02Q06	IC02Q07	IC03Q01	IC04Q01	IC05Q01	IC06Q01	IC07Q01	IC08Q01	IC08Q02	IC08Q03	IC08Q04	IC08Q05	IC08Q06	IC08Q07	IC08Q08	IC08Q09	IC08Q11	IC09Q01	IC09Q02	IC09Q03	IC09Q04	IC09Q05	IC09Q06	IC09Q07	IC10Q01	IC10Q02	IC10Q03	IC10Q04	IC10Q05	IC10Q06	IC10Q07	IC10Q08	IC10Q09	IC11Q01	IC11Q02	IC11Q03	IC11Q04	IC11Q05	IC11Q06	IC11Q07	IC22Q01	IC22Q02	IC22Q04	IC22Q06	IC22Q07	IC22Q08	EC01Q01	EC02Q01	EC03Q01	EC03Q02	EC03Q03	EC03Q04	EC03Q05	EC03Q06	EC03Q07	EC03Q08	EC03Q09	EC03Q10	EC04Q01A	EC04Q01B	EC04Q01C	EC04Q02A	EC04Q02B	EC04Q02C	EC04Q03A	EC04Q03B	EC04Q03C	EC04Q04A	EC04Q04B	EC04Q04C	EC04Q05A	EC04Q05B	EC04Q05C	EC04Q06A	EC04Q06B	EC04Q06C	EC05Q01	EC06Q01	EC07Q01	EC07Q02	EC07Q03	EC07Q04	EC07Q05	EC08Q01	EC08Q02	EC08Q03	EC08Q04	EC09Q03	EC10Q01	EC11Q02	EC11Q03	EC12Q01	ST22Q01	ST23Q01	ST23Q02	ST23Q03	ST23Q04	ST23Q05	ST23Q06	ST23Q07	ST23Q08	ST24Q01	ST24Q02	ST24Q03	CLCUSE1	CLCUSE301	CLCUSE302	DEFFORT	QUESTID	BOOKID	EASY	AGE	GRADE	PROGN	ANXMAT	ATSCHL	ATTLNACT	BELONG	BFMJ2	BMMJ1	CLSMAN	COBN_F	COBN_M	COBN_S	COGACT	CULTDIST	CULTPOS	DISCLIMA	ENTUSE	ESCS	EXAPPLM	EXPUREM	FAILMAT	FAMCON	FAMCONC	FAMSTRUC	FISCED	HEDRES	HERITCUL	HISCED	HISEI	HOMEPOS	HOMSCH	HOSTCUL	ICTATTNEG	ICTATTPOS	ICTHOME	ICTRES	ICTSCH	IMMIG	INFOCAR	INFOJOB1	INFOJOB2	INSTMOT	INTMAT	ISCEDD	ISCEDL	ISCEDO	LANGCOMM	LANGN	LANGRPPD	LMINS	MATBEH	MATHEFF	MATINTFC	MATWKETH	MISCED	MMINS	MTSUP	OCOD1	OCOD2	OPENPS	OUTHOURS	PARED	PERSEV	REPEAT	SCMAT	SMINS	STUDREL	SUBNORM	TCHBEHFA	TCHBEHSO	TCHBEHTD	TEACHSUP	TESTLANG	TIMEINT	USEMATH	USESCH	WEALTH	ANCATSCHL	ANCATTLNACT	ANCBELONG	ANCCLSMAN	ANCCOGACT	ANCINSTMOT	ANCINTMAT	ANCMATWKETH	ANCMTSUP	ANCSCMAT	ANCSTUDREL	ANCSUBNORM	PV1MATH	PV2MATH	PV3MATH	PV4MATH	PV5MATH	PV1MACC	PV2MACC	PV3MACC	PV4MACC	PV5MACC	PV1MACQ	PV2MACQ	PV3MACQ	PV4MACQ	PV5MACQ	PV1MACS	PV2MACS	PV3MACS	PV4MACS	PV5MACS	PV1MACU	PV2MACU	PV3MACU	PV4MACU	PV5MACU	PV1MAPE	PV2MAPE	PV3MAPE	PV4MAPE	PV5MAPE	PV1MAPF	PV2MAPF	PV3MAPF	PV4MAPF	PV5MAPF	PV1MAPI	PV2MAPI	PV3MAPI	PV4MAPI	PV5MAPI	PV1READ	PV2READ	PV3READ	PV4READ	PV5READ	PV1SCIE	PV2SCIE	PV3SCIE	PV4SCIE	PV5SCIE	W_FSTUWT	W_FSTR1	W_FSTR2	W_FSTR3	W_FSTR4	W_FSTR5	W_FSTR6	W_FSTR7	W_FSTR8	W_FSTR9	W_FSTR10	W_FSTR11	W_FSTR12	W_FSTR13	W_FSTR14	W_FSTR15	W_FSTR16	W_FSTR17	W_FSTR18	W_FSTR19	W_FSTR20	W_FSTR21	W_FSTR22	W_FSTR23	W_FSTR24	W_FSTR25	W_FSTR26	W_FSTR27	W_FSTR28	W_FSTR29	W_FSTR30	W_FSTR31	W_FSTR32	W_FSTR33	W_FSTR34	W_FSTR35	W_FSTR36	W_FSTR37	W_FSTR38	W_FSTR39	W_FSTR40	W_FSTR41	W_FSTR42	W_FSTR43	W_FSTR44	W_FSTR45	W_FSTR46	W_FSTR47	W_FSTR48	W_FSTR49	W_FSTR50	W_FSTR51	W_FSTR52	W_FSTR53	W_FSTR54	W_FSTR55	W_FSTR56	W_FSTR57	W_FSTR58	W_FSTR59	W_FSTR60	W_FSTR61	W_FSTR62	W_FSTR63	W_FSTR64	W_FSTR65	W_FSTR66	W_FSTR67	W_FSTR68	W_FSTR69	W_FSTR70	W_FSTR71	W_FSTR72	W_FSTR73	W_FSTR74	W_FSTR75	W_FSTR76	W_FSTR77	W_FSTR78	W_FSTR79	W_FSTR80	WVARSTRR	VAR_UNIT	SENWGT_STU	VER_STU
1	Albania	80000	ALB0006	Non-OECD	Albania	1	1	10	1.0	2	1996	Female	No	6.0	No, never	No, never	No, never	None	None	1.0	Yes	Yes	Yes	Yes	NaN	NaN	<ISCED level 3A>	No	No	No	No	Other (e.g. home duties, retired)	<ISCED level 3A>	NaN	NaN	NaN	NaN	Working part-time <for pay>	Country of test	Country of test	Country of test	NaN	Language of the test	Yes	No	Yes	No	No	No	No	Yes	No	Yes	No	Yes	No	Yes	8002	8001	8002	Two	One	NaN	NaN	NaN	0-10 books	Agree	Strongly agree	Agree	Agree	Agree	Agree	Agree	Strongly agree	Disagree	Agree	Disagree	Agree	Agree	Agree	Not at all confident	Not very confident	Confident	Confident	Confident	Not at all confident	Confident	Very confident	Agree	Disagree	Agree	Agree	Agree	Agree	Agree	Disagree	Disagree	Disagree	Agree	Disagree	Disagree	Agree	NaN	Disagree	Likely	Slightly likely	Likely	Likely	Likely	Very Likely	Agree	Agree	Agree	Agree	Agree	Agree	Agree	Agree	Agree	Courses after school Test Language	Major in college Science	Study harder Test Language	Maximum classes Science	Pursuing a career Math	Often	Sometimes	Sometimes	Sometimes	Sometimes	Never or rarely	Never or rarely	Never or rarely	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Never or Hardly Ever	Most Lessons	Never or Hardly Ever	Every Lesson	Most Lessons	Every Lesson	Every Lesson	Every Lesson	Never or Hardly Ever	Most Lessons	Every Lesson	Every Lesson	Every Lesson	Always or almost always	Sometimes	Never or rarely	Always or almost always	Always or almost always	Always or almost always	Always or almost always	Often	Often	Never or Hardly Ever	Never or Hardly Ever	Never or Hardly Ever	Never or Hardly Ever	Never or Hardly Ever	Strongly disagree	Strongly disagree	Strongly disagree	Strongly disagree	Agree	Agree	Agree	Strongly agree	Strongly agree	Disagree	Agree	Strongly disagree	Disagree	Agree	Agree	Strongly disagree	Agree	Agree	Disagree	Agree	Agree	Strongly disagree	Strongly agree	Strongly agree	Strongly disagree	Agree	Strongly disagree	Agree	Agree	Strongly agree	Strongly disagree	Strongly disagree	Agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly disagree	Disagree	Strongly disagree	Very much like me	Very much like me	Very much like me	Somewhat like me	Very much like me	Somewhat like me	Mostly like me	Mostly like me	Mostly like me	Somewhat like me	definitely do this	definitely do this	definitely do this	definitely do this	4.0	2.0	1.0	1.0	1.0	2.0	1.0	1.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	A Simple calculator	99	99	99	StQ Form B	booklet 7	Standard set of booklets	16.17	0.0	Albania: Upper secondary education	0.32	-2.31	0.5206	-1.18	76.49	79.74	-1.3771	Albania	Albania	Albania	0.6994	NaN	-0.48	1.85	NaN	NaN	NaN	NaN	0.6400	NaN	NaN	2.0	ISCED 3A, ISCED 4	-1.29	NaN	ISCED 3A, ISCED 4	NaN	-2.61	NaN	NaN	NaN	NaN	NaN	-3.16	NaN	Native	NaN	NaN	NaN	0.80	0.91	A	ISCED level 3	General	NaN	Albanian	NaN	NaN	0.6426	-0.77	-0.7332	0.2882	ISCED 3A, ISCED 4	NaN	-0.9508	Building architects	Primary school teachers	0.0521	NaN	12.0	-0.3407	Did not repeat a <grade>	0.41	NaN	-1.04	-0.0455	1.3625	0.9374	0.4297	1.68	Albanian	NaN	NaN	NaN	-2.92	-1.8636	-0.6779	-0.7351	-0.7808	-0.0219	-0.1562	0.0486	-0.2199	-0.5983	-0.0807	-0.5901	-0.3346	406.8469	376.4683	344.5319	321.1637	381.9209	325.8374	324.2795	279.8800	267.4170	312.5954	409.1837	388.1524	373.3525	389.7102	415.4152	351.5423	375.6894	341.4161	386.5945	426.3203	396.7207	334.4057	328.9531	339.8582	354.6580	324.2795	345.3108	381.1419	380.3630	346.8687	319.6059	345.3108	360.8895	390.4892	322.7216	290.7852	345.3108	326.6163	407.6258	367.1210	249.5762	254.3420	406.8496	175.7053	218.5981	341.7009	408.8400	348.2283	367.8105	392.9877	8.9096	13.1249	13.0829	4.5315	13.0829	13.9235	13.1249	13.1249	4.3389	4.3313	13.7954	4.5315	4.3313	13.7954	13.9235	4.3389	4.3313	4.5084	4.5084	13.7954	4.5315	13.1249	13.0829	4.5315	13.0829	13.9235	13.1249	13.1249	4.3389	4.3313	13.7954	4.5315	4.3313	13.7954	13.9235	4.3389	4.3313	4.5084	4.5084	13.7954	4.5315	4.5084	4.5315	13.0829	4.5315	4.3313	4.5084	4.5084	13.7954	13.9235	4.3389	13.0829	13.9235	4.3389	4.3313	13.7954	13.9235	13.1249	13.1249	4.3389	13.0829	4.5084	4.5315	13.0829	4.5315	4.3313	4.5084	4.5084	13.7954	13.9235	4.3389	13.0829	13.9235	4.3389	4.3313	13.7954	13.9235	13.1249	13.1249	4.3389	13.0829	19	1	0.2098	22NOV13
2	Albania	80000	ALB0006	Non-OECD	Albania	1	2	10	1.0	2	1996	Female	Yes, for more than one year	7.0	No, never	No, never	No, never	One or two times	None	1.0	Yes	Yes	NaN	Yes	NaN	NaN	<ISCED level 3A>	Yes	Yes	No	No	Working full-time <for pay>	<ISCED level 3A>	No	No	No	No	Working full-time <for pay>	Country of test	Country of test	Country of test	NaN	Language of the test	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	8001	8001	8002	Three or more	Three or more	Three or more	Two	Two	201-500 books	Disagree	Strongly agree	Disagree	Disagree	Agree	Agree	Disagree	Disagree	Strongly agree	Strongly agree	Disagree	Agree	Disagree	Agree	Confident	Very confident	Very confident	Confident	Very confident	Confident	Very confident	Not very confident	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Strongly agree	Strongly agree	Strongly disagree	Disagree	Agree	Disagree	Likely	Slightly likely	Slightly likely	Very Likely	Slightly likely	Likely	Agree	Agree	Strongly agree	Strongly agree	Strongly agree	Agree	Agree	Disagree	Agree	Courses after school Math	Major in college Science	Study harder Math	Maximum classes Science	Pursuing a career Science	Sometimes	Often	Always or almost always	Sometimes	Always or almost always	Never or rarely	Never or rarely	Often	relating to known	Improve understanding	in my sleep	Repeat examples	I do not attend <out-of-school time lessons> in this subject	2 or more but less than 4 hours a week	2 or more but less than 4 hours a week	Less than 2 hours a week	NaN	NaN	6.0	0.0	0.0	2.0	Rarely	Rarely	Frequently	Sometimes	Frequently	Sometimes	Frequently	Never	Frequently	Know it well, understand the concept	Know it well, understand the concept	Heard of it once or twice	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	Never heard of it	Know it well, understand the concept	Know it well, understand the concept	Never heard of it	Know it well, understand the concept	Heard of it once or twice	Know it well, understand the concept	Know it well, understand the concept	Never heard of it	Heard of it often	45.0	45.0	45.0	7.0	6.0	2.0	NaN	30.0	Frequently	Sometimes	Frequently	Frequently	Sometimes	Sometimes	Sometimes	Sometimes	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Not at all like me	Not at all like me	Mostly like me	Somewhat like me	Very much like me	Somewhat like me	Not much like me	Not much like me	Mostly like me	Not much like me	probably not do this	probably do this	probably not do this	probably do this	1.0	2.0	3.0	2.0	2.0	3.0	1.0	1.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	A Simple calculator	99	99	99	StQ Form A	booklet 9	Standard set of booklets	16.17	0.0	Albania: Upper secondary education	NaN	NaN	NaN	NaN	15.35	23.47	NaN	Albania	Albania	Albania	NaN	NaN	1.27	NaN	NaN	NaN	-0.0681	0.7955	0.1524	0.6387	-0.08	2.0	ISCED 3A, ISCED 4	1.12	NaN	ISCED 5A, 6	NaN	1.41	NaN	NaN	NaN	NaN	NaN	1.15	NaN	Native	NaN	NaN	NaN	-0.39	0.00	A	ISCED level 3	General	NaN	Albanian	NaN	315.0	1.4702	0.34	-0.2514	0.6490	ISCED 5A, 6	270.0	NaN	Tailors, dressmakers, furriers and hatters	Building construction labourers	-0.9492	8.0	16.0	1.3116	Did not repeat a <grade>	NaN	90.0	NaN	0.6602	NaN	NaN	NaN	NaN	Albanian	NaN	NaN	NaN	0.69	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	486.1427	464.3325	453.4273	472.9008	476.0165	325.6816	419.9330	378.6493	359.9548	384.1019	373.1968	444.0801	456.5431	401.2385	461.2167	366.9653	459.6588	426.1645	423.0488	443.3011	389.5544	438.6275	417.5962	379.4283	438.6275	440.1854	456.5431	486.9216	458.1010	444.0801	411.3647	437.8486	457.3220	454.2063	460.4378	434.7328	448.7537	494.7110	429.2803	434.7328	406.2936	349.8975	400.7334	369.7553	396.7618	548.9929	471.5964	471.5964	443.6218	454.8116	8.9096	13.1249	13.0829	4.5315	13.0829	13.9235	13.1249	13.1249	4.3389	4.3313	13.7954	4.5315	4.3313	13.7954	13.9235	4.3389	4.3313	4.5084	4.5084	13.7954	4.5315	13.1249	13.0829	4.5315	13.0829	13.9235	13.1249	13.1249	4.3389	4.3313	13.7954	4.5315	4.3313	13.7954	13.9235	4.3389	4.3313	4.5084	4.5084	13.7954	4.5315	4.5084	4.5315	13.0829	4.5315	4.3313	4.5084	4.5084	13.7954	13.9235	4.3389	13.0829	13.9235	4.3389	4.3313	13.7954	13.9235	13.1249	13.1249	4.3389	13.0829	4.5084	4.5315	13.0829	4.5315	4.3313	4.5084	4.5084	13.7954	13.9235	4.3389	13.0829	13.9235	4.3389	4.3313	13.7954	13.9235	13.1249	13.1249	4.3389	13.0829	19	1	0.2098	22NOV13
3	Albania	80000	ALB0006	Non-OECD	Albania	1	3	9	1.0	9	1996	Female	Yes, for more than one year	6.0	No, never	No, never	No, never	None	None	1.0	Yes	Yes	No	Yes	No	No	<ISCED level 3B, 3C>	Yes	Yes	Yes	No	Working full-time <for pay>	<ISCED level 3A>	Yes	No	Yes	Yes	Working full-time <for pay>	Country of test	Country of test	Country of test	NaN	Language of the test	Yes	Yes	Yes	Yes	No	Yes	Yes	Yes	Yes	Yes	No	Yes	No	Yes	8001	8001	8001	Three or more	Two	Two	One	Two	More than 500 books	Agree	Strongly agree	Agree	Agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly agree	Agree	Confident	Very confident	Very confident	Confident	Very confident	Not very confident	Very confident	Confident	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Strongly agree	Agree	Strongly agree	Strongly disagree	Strongly agree	Strongly disagree	Likely	Likely	Very Likely	Very Likely	Very Likely	Slightly likely	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly agree	Strongly agree	Courses after school Math	Major in college Science	Study harder Math	Maximum classes Science	Pursuing a career Science	Sometimes	Always or almost always	Sometimes	Never or rarely	Always or almost always	Never or rarely	Never or rarely	Never or rarely	Most important	Improve understanding	learning goals	more information	Less than 2 hours a week	2 or more but less than 4 hours a week	4 or more but less than 6 hours a week	I do not attend <out-of-school time lessons> in this subject	NaN	6.0	6.0	7.0	2.0	3.0	Frequently	Sometimes	Frequently	Rarely	Frequently	Rarely	Frequently	Sometimes	Frequently	Never heard of it	Know it well, understand the concept	Heard of it once or twice	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	Heard of it once or twice	Know it well, understand the concept	Know it well, understand the concept	Heard of it once or twice	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	Know it well, understand the concept	60.0	NaN	NaN	5.0	4.0	2.0	24.0	30.0	Frequently	Frequently	Frequently	Frequently	Frequently	Frequently	Rarely	Rarely	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Not much like me	Not much like me	Very much like me	Very much like me	Somewhat like me	Mostly like me	Mostly like me	Very much like me	Mostly like me	Very much like me	probably not do this	definitely do this	definitely not do this	probably do this	1.0	3.0	4.0	1.0	3.0	4.0	1.0	1.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	A Simple calculator	99	99	99	StQ Form A	booklet 3	Standard set of booklets	15.58	-1.0	Albania: Lower secondary education	NaN	NaN	NaN	NaN	22.57	NaN	NaN	Albania	Albania	Albania	NaN	NaN	1.27	NaN	NaN	NaN	0.5359	0.7955	1.2219	0.8215	-0.89	2.0	ISCED 5A, 6	-0.69	NaN	ISCED 5A, 6	NaN	0.14	NaN	NaN	NaN	NaN	NaN	-0.40	NaN	Native	NaN	NaN	NaN	1.59	1.23	A	ISCED level 2	General	NaN	Albanian	NaN	300.0	0.9618	0.34	-0.2514	2.0389	ISCED 5A, 6	NaN	NaN	Housewife	Bricklayers and related workers	0.9383	24.0	16.0	0.9918	Did not repeat a <grade>	NaN	NaN	NaN	2.2350	NaN	NaN	NaN	NaN	Albanian	NaN	NaN	NaN	-0.23	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	533.2684	481.0796	489.6479	490.4269	533.2684	611.1622	486.5322	567.5417	541.0578	544.9525	597.1413	495.1005	576.8889	507.5635	556.6365	594.8045	473.2902	554.2997	537.1631	568.3206	471.7324	431.2276	460.8272	419.5435	456.9325	559.7523	501.3320	555.0787	467.0587	506.7845	580.7836	481.0796	555.0787	453.8168	491.2058	527.0369	444.4695	516.1318	403.9648	476.4060	401.2100	404.3872	387.7067	431.3938	401.2100	499.6643	428.7952	492.2044	512.7191	499.6643	8.4871	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	19	1	0.1999	22NOV13
4	Albania	80000	ALB0006	Non-OECD	Albania	1	4	9	1.0	8	1996	Female	Yes, for more than one year	6.0	No, never	No, never	No, never	None	None	1.0	Yes	Yes	No	Yes	No	No	<ISCED level 3B, 3C>	No	No	No	No	Working full-time <for pay>	<ISCED level 3A>	Yes	Yes	No	No	Working full-time <for pay>	Country of test	Country of test	Country of test	NaN	Language of the test	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No	Yes	Yes	No	8001	8001	8002	Three or more	Two	One	NaN	One	11-25 books	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Strongly agree	Disagree	Agree	Agree	Disagree	Strongly agree	Disagree	Agree	Agree	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	relating to known	new ways	learning goals	more information	I do not attend <out-of-school time lessons> in this subject	I do not attend <out-of-school time lessons> in this subject	Less than 2 hours a week	I do not attend <out-of-school time lessons> in this subject	10.0	2.0	2.0	0.0	0.0	3.0	Sometimes	Sometimes	Sometimes	Sometimes	Frequently	Sometimes	Frequently	Rarely	Frequently	Heard of it often	Heard of it often	Heard of it often	Know it well, understand the concept	Heard of it a few times	Know it well, understand the concept	Never heard of it	Know it well, understand the concept	Know it well, understand the concept	Never heard of it	Know it well, understand the concept	Never heard of it	Know it well, understand the concept	Know it well, understand the concept	Heard of it often	Heard of it often	45.0	45.0	45.0	3.0	3.0	2.0	NaN	28.0	Frequently	Sometimes	Frequently	Rarely	Frequently	Frequently	Sometimes	Sometimes	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	NaN	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Every Lesson	Never or Hardly Ever	Most Lessons	Every Lesson	Every Lesson	Always or almost always	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Never or rarely	Never or Hardly Ever	Never or Hardly Ever	Never or Hardly Ever	Never or Hardly Ever	NaN	NaN	NaN	Strongly agree	Strongly agree	Strongly agree	Strongly agree	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	StQ Form C	booklet 2	Standard set of booklets	15.67	-1.0	Albania: Lower secondary education	0.31	NaN	NaN	NaN	14.21	NaN	NaN	Albania	Albania	Albania	-0.3788	NaN	1.27	1.80	NaN	NaN	0.3220	0.7955	NaN	0.7266	0.24	2.0	ISCED 5A, 6	0.04	NaN	ISCED 5A, 6	NaN	-0.73	NaN	NaN	NaN	NaN	NaN	-0.40	NaN	Native	NaN	NaN	NaN	NaN	NaN	A	ISCED level 2	General	NaN	Albanian	NaN	135.0	NaN	NaN	NaN	NaN	ISCED 3B, C	135.0	1.6748	Housewife	Cleaners and helpers in offices, hotels and other establishm	NaN	17.0	16.0	NaN	Did not repeat a <grade>	0.18	90.0	NaN	NaN	0.7644	3.3108	2.3916	1.68	Albanian	NaN	NaN	NaN	-1.17	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	412.2215	498.6836	415.3373	466.7472	454.2842	538.4094	511.9255	553.9882	483.8838	479.2102	525.1675	529.0622	539.1883	516.5992	501.7993	658.3658	567.2301	669.2709	652.1343	645.1239	508.0308	522.0517	524.3885	495.5678	458.1788	524.3885	462.0735	494.0100	459.7367	471.4208	534.5147	455.8420	504.1362	454.2842	483.8838	521.2728	481.5470	503.3572	469.8629	478.4312	547.3630	481.4353	461.5776	425.0393	471.9036	438.6796	481.5740	448.9370	474.1141	426.5573	8.4871	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	19	1	0.1999	22NOV13
5	Albania	80000	ALB0006	Non-OECD	Albania	1	5	9	1.0	10	1996	Female	Yes, for more than one year	6.0	No, never	No, never	No, never	One or two times	None	2.0	Yes	Yes	Yes	NaN	NaN	NaN	She did not complete <ISCED level 1>	No	No	No	No	Working part-time <for pay>	<ISCED level 3B, 3C>	No	No	No	Yes	Working part-time <for pay>	Country of test	Country of test	Country of test	NaN	Language of the test	Yes	Yes	No	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No	Yes	Yes	Yes	8001	8002	8001	Two	One	Two	NaN	One	101-200 books	Disagree	Strongly agree	Disagree	Disagree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Agree	Confident	Very confident	NaN	Very confident	Very confident	Confident	Very confident	Not very confident	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly agree	Disagree	Disagree	Disagree	Agree	Agree	Strongly agree	Strongly agree	Disagree	Disagree	Strongly agree	Disagree	Likely	Likely	Likely	Likely	Slightly likely	Very Likely	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly agree	Strongly agree	Courses after school Test Language	Major in college Math	Study harder Math	Maximum classes Math	Pursuing a career Math	Always or almost always	Always or almost always	Often	Often	Sometimes	NaN	Sometimes	Sometimes	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	Every Lesson	Most Lessons	Every Lesson	Most Lessons	Some Lessons	Some Lessons	Some Lessons	Most Lessons	Some Lessons	Most Lessons	Every Lesson	Most Lessons	Every Lesson	Some Lessons	Most Lessons	Most Lessons	Every Lesson	Most Lessons	Always or almost always	Often	Sometimes	Often	Often	Often	Always or almost always	Often	Often	Some Lessons	Some Lessons	NaN	Most Lessons	Never or Hardly Ever	Strongly disagree	Disagree	Strongly agree	Strongly agree	Agree	Strongly agree	Agree	Disagree	Strongly agree	Disagree	Agree	Agree	Strongly agree	Agree	Agree	Agree	Agree	Agree	Agree	Strongly disagree	Strongly agree	Strongly agree	Strongly disagree	Strongly agree	Strongly disagree	Strongly agree	Strongly agree	Strongly agree	Disagree	Strongly disagree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Strongly agree	Agree	Strongly agree	Strongly disagree	Agree	Strongly agree	Disagree	NaN	Mostly like me	Very much like me	Very much like me	Very much like me	Very much like me	Very much like me	Mostly like me	Very much like me	Mostly like me	definitely do this	definitely do this	definitely do this	definitely do this	1.0	2.0	1.0	2.0	1.0	2.0	1.0	1.0	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	99	99	99	StQ Form B	booklet 4	Standard set of booklets	15.50	-1.0	Albania: Lower secondary education	1.02	1.38	1.2115	2.63	80.92	NaN	-0.0784	Albania	Albania	Albania	0.5403	NaN	1.27	-0.08	NaN	NaN	NaN	NaN	0.6400	NaN	NaN	2.0	ISCED 3A, ISCED 4	-0.69	NaN	ISCED 3A, ISCED 4	NaN	-0.57	NaN	NaN	NaN	NaN	NaN	0.24	NaN	Native	NaN	NaN	NaN	1.59	0.30	A	ISCED level 2	General	NaN	Albanian	NaN	NaN	1.8169	0.41	0.6584	1.6881	NaN	NaN	0.6709	Housewife	Economists	1.2387	NaN	12.0	1.0819	Did not repeat a <grade>	-0.06	NaN	-0.02	2.8039	0.7644	0.9374	0.4297	0.11	Albanian	NaN	NaN	NaN	-1.17	0.6517	0.4908	0.8675	0.0505	0.4940	0.9986	0.0486	0.9341	0.4052	0.0358	0.2492	1.2260	381.9209	328.1742	403.7311	418.5309	395.1628	373.3525	293.1220	364.0053	430.2150	403.7311	414.6362	385.8155	392.8260	448.9095	474.6144	417.7520	353.1002	424.7624	457.4778	459.0357	339.0793	309.4797	340.6372	369.4579	384.2577	373.3525	392.0470	347.6476	342.1950	342.1950	432.5518	431.7729	399.0575	369.4579	341.4161	297.0167	353.8791	347.6476	314.1533	311.0375	311.7707	141.7883	293.5015	272.8495	260.1405	361.5628	275.7740	372.7527	403.5248	422.1746	8.4871	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	12.7307	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	4.2436	4.2436	12.7307	4.2436	4.2436	4.2436	4.2436	12.7307	12.7307	4.2436	12.7307	12.7307	4.2436	4.2436	12.7307	12.7307	12.7307	12.7307	4.2436	12.7307	19	1	0.1999	22NOV13

How is total performance distributed among participants?¶

It shows the frequency distribution of participants' total performance scores, suggesting a roughly normal distribution with a peak around the 400-500 range.¶

What is the distribution of educational levels among participants?¶

This histogram displays the count of participants according to the number of years of education they have completed, with notable peaks at 12 and 16 years, suggesting high school and college education levels respectively.¶

What is the age distribution of participants?¶

The histogram shows that participant ages are concentrated around 15-16 years, which could indicate a study involving high school students.¶

Is there a difference in math performance between genders?¶

The box plot compares the distribution of math performance scores between male (1) and female (0) participants. It indicates median performance and the range of scores for each gender.¶

How does math performance vary across different age groups?¶

It provides a box plot for each age group, showing the central tendency and spread of math performance within those groups.¶

Is there a correlation between socioeconomic status and total performance¶

The scatter plot depicts individual data points representing participants, colored by gender, against socioeconomic index scores and their corresponding total performance.¶

What is the average socioeconomic status in each country?¶

The bar chart ranks countries by their average socioeconomic status.¶

How does average reading performance compare between genders across different countries?¶

It shows a side-by-side comparison of male and female reading performance averages for each country.¶

What is the gender distribution among participants?¶

It's a pie chart illustrating the percentage of male and female participants, indicating a nearly even split.¶

What is the cumulative distribution of socioeconomic status among participants?¶

It shows how the socioeconomic status of participants accumulates across the range of status levels.¶

How many participants are there from each country in this study?¶

It displays the number of participants from various countries, with some countries having significantly higher numbers of participants than others.¶

What is the percentage of male and female participants in each country?¶

Each bar represents a country with proportions of male and female participants stacked on top of each other, showing gender distribution across countries.¶

What is the distribution of total scores among participants, and how does the average score differ by gender across countries?¶

The box plots show the interquartile range (IQR) of total scores in various countries, with markers indicating the average scores for males and females.¶

What is the distribution of student scores by gender?¶

The plot compares the distribution curves for male and female participants, showing where scores are most concentrated.¶

How are student scores distributed across different subjects by gender?¶

There are separate density plots for math, reading, and science scores, each comparing the score distributions for male and female students.¶

What is the relationship between student scores and their socioeconomic background?¶

This hexbin plot shows concentrations of student scores against socioeconomic index, with a color density indicating the frequency of scores. The correlation coefficient (ρ) suggests the strength of the relationship.¶

How do parental factors such as education, occupation, and home setup influence student scores across different subjects?¶

Each scatter plot shows student scores against different parental indices for math, reading, and science. Correlation coefficients are provided for each factor's relationship with the scores.¶

	x
Age	Age of student
Occupational	Highest parental occupational status
Education	Highest parental education in years
Home Setup	Home Possessions
Socioeconomic	Index of economic, social and cultural status